European Identity THeft Observatory System

Informazioni relative al progetto

EITHOS

ID dell’accordo di sovvenzione: 101073928

DOI

10.3030/101073928

Progetto chiuso

Data della firma CE 18 Luglio 2022

Data di avvio 1 Ottobre 2022

Data di completamento 30 Settembre 2025

Finanziato da

• Civil Security for Society

Costo totale

€ 2 996 141,25

Contributo UE

€ 2 996 141,25

Coordinato da

ETHNIKO KENTRO EREVNAS KAI TECHNOLOGIKIS ANAPTYXIS
Greece

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Documents, reports (5)

Project Management Plan & Handbook

The project handbook will outline the processes that will be followed and used during the projects lifetime in terms of reporting communicating and document handling

Data Management Plan v1

The data management plan will define how the various kinds of data collected and generated in the project will be handled and stored It will be a report of the planned processing operations and their purposes as well as an assessment of the necessity of personal data processing in relation to the purposes It also set the requirements for data store in terms of security and privacy protection It will be maintained as a living document

Relevant legal and ethical frameworks v1

The deliverable will describe legal and ethical frameworks that are related to EITHOS That is frameworks that are related to security privacy and the ethical processing of data and will provide the guidelines for lawful and ethical developments in EITHOS

EITHOS Dissemination, Communication, Exploitation, and Sustainability v1

This deliverable will describe the activities within this WP and will be constituted by three 3 iterations The first one will provide a description of the plan and strategies that EITHOS will follow for reaching significant amounts of citizens and LEAs The second version will describe the materialisation of the awareness campaigns as well as the results gathered within the related activities as well as an initial plan for the observatorys sustainability The third and final version will provide further information regarding the campaigns as well as EITHOS training packages for LEAs to conclude with a concrete plan on the sustainability of EITHOS

EITHOS Awareness Campaigns v1

This deliverable will be reporting EITHOS strategy and approach to the projects awareness campaigns v1 as well as the projects activities performed to reach EITHOS awareness related objectives v2 v3

Pubblicazioni

Peer reviewed articles (4)

A Dual-Branch Fusion Model for Deepfake Detection Using Video Frames and Microexpression Features

Autori: Georgios Petmezas, Vazgken Vanian, Manuel Pastor Rufete, Eleana E. I. Almaloglou, Dimitris Zarpalas
Pubblicato in: Journal of Imaging, Numero 11, 2025, ISSN 2313-433X
Editore: MDPI AG
DOI: 10.3390/JIMAGING11070231

Video deepfake detection using a hybrid CNN-LSTM-Transformer model for identity verification

Autori: Georgios Petmezas, Vazgken Vanian, Konstantinos Konstantoudakis, Elena E. I. Almaloglou, Dimitris Zarpalas
Pubblicato in: Multimedia Tools and Applications, Numero 84, 2025, ISSN 1573-7721
Editore: Springer Science and Business Media LLC
DOI: 10.1007/S11042-024-20548-6

ReenactFaces: A Specialized Dataset for Reenactment-Based Deepfake Detection

Autori: Vazgken Vanian, Georgios Petmezas, Konstantinos Konstantoudakis, Dimitris Zarpalas
Pubblicato in: Lecture Notes on Data Engineering and Communications Technologies, Advanced Information Networking and Applications, 2025, ISSN 0000-0000
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-87784-1_35

XDF: A Large-Scale Dataset for Evaluating Video Deepfake Detection Across Multiple Manipulation Techniques

Autori: Vazgken Vanian, Georgios Petmezas, Konstantinos Konstantoudakis, Dimitris Zarpalas
Pubblicato in: Proceedings of the 4th ACM International Workshop on Multimedia AI against Disinformation, 2025, ISSN 0000-0000
Editore: ACM
DOI: 10.1145/3733567.3735569

Conference proceedings (5)

The Vicomtech partial deepfake detection and location system for the 2023 ADD Challenge

Autori: Martín-Doñas, Juan Manuel; Álvarez Muniain, Aitor
Pubblicato in: 2023, ISSN 1613-0073
Editore: CEUR
DOI: 10.5281/zenodo.10021600

MGAMNET: A Mask-Guided Attention Network for Deepfake Detection

Autori: Vazgken Vanian, Georgios Petmezas, Eleana E.I. Almaloglou, Dimitris Zarpalas
Pubblicato in: 2025 25th International Conference on Digital Signal Processing (DSP), 2025
Editore: IEEE
DOI: 10.1109/DSP65409.2025.11075024

Exploring Self-supervised Embeddings and Synthetic Data Augmentation for Robust Audio Deepfake Detection

Autori: Juan M. Martín-Doñas, Aitor Álvarez, Eros Rosello, Angel M. Gomez, Antonio M. Peinado
Pubblicato in: Interspeech 2024, 2024
Editore: ISCA
DOI: 10.21437/INTERSPEECH.2024-942

Anti-spoofing Ensembling Model: Dynamic Weight Allocation in Ensemble Models for Improved Voice Biometrics Security

Autori: Eros Rosello, Angel M. Gomez, Iván López-Espejo, Antonio M. Peinado, Juan M. Martín-Doñas
Pubblicato in: Interspeech 2024, 2024
Editore: ISCA
DOI: 10.21437/INTERSPEECH.2024-403

ASASVIcomtech: the Vicomtech-UGR speech deepfake detection and SASV systems for the ASVspoof5 Challenge

Autori: Juan M. Martín-Doñas, Eros Rosello, Angel M. Gomez, Aitor Álvarez, Iván López-Espejo, Antonio M. Peinado
Pubblicato in: The Automatic Speaker Verification Spoofing Countermeasures Workshop (ASVspoof 2024), 2024
Editore: ISCA
DOI: 10.21437/ASVSPOOF.2024-21